ZeroDL: Zero-shot Distribution Learning for Text Clustering via Large Language Models
Hwiyeol Jo, Hyunwoo Lee, Kang Min Yoo, Taiwoo Park
Abstract
The advancements in large language models (LLMs) have brought significant progress in NLP tasks. However, if a task cannot be fully described in prompts, the models could fail to carry out the task. In this paper, we propose a simple yet effective method to contextualize a task toward a LLM. The method utilizes (1) open-ended zero-shot inference from the entire dataset, (2) aggregate the inference results, and (3) finally incorporate the aggregated meta-information for the actual task. We show the effectiveness in text clustering tasks, empowering LLMs to perform text-to-text-based clustering and leading to improvements on several datasets. Furthermore, we explore the generated class labels for clustering, showing how the LLM understands the task through data.
BibTeX
@inproceedings{jo-etal-2025-zerodl,
title = "{Z}ero{DL}: Zero-shot Distribution Learning for Text Clustering via Large Language Models",
author = "Jo, Hwiyeol and
Lee, Hyunwoo and
Yoo, Kang Min and
Park, Taiwoo",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.1005/",
doi = "10.18653/v1/2025.findings-acl.1005",
pages = "19597--19607",
ISBN = "979-8-89176-256-5"
}